summaryrefslogtreecommitdiff
path: root/Master/tlpkg/tlperl/lib/CORE/utfebcdic.h
diff options
context:
space:
mode:
Diffstat (limited to 'Master/tlpkg/tlperl/lib/CORE/utfebcdic.h')
-rw-r--r--Master/tlpkg/tlperl/lib/CORE/utfebcdic.h66
1 files changed, 31 insertions, 35 deletions
diff --git a/Master/tlpkg/tlperl/lib/CORE/utfebcdic.h b/Master/tlpkg/tlperl/lib/CORE/utfebcdic.h
index eff444e7fde..e7f5f32c69f 100644
--- a/Master/tlpkg/tlperl/lib/CORE/utfebcdic.h
+++ b/Master/tlpkg/tlperl/lib/CORE/utfebcdic.h
@@ -152,7 +152,7 @@ unsigned char PL_utf8skip[] = {
* remains 'A' */
#if '^' == 95 /* if defined(__MVS__) || defined(??) (VM/ESA?) 1047 */
-EXTCONST unsigned char PL_utf2e[] = { /* I8 to EBCDIC (IBM-1047) */
+EXTCONST unsigned char PL_utf2e[] = { /* I8 to UTFEBCDIC (IBM-1047) */
0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
@@ -171,7 +171,7 @@ EXTCONST unsigned char PL_utf2e[] = { /* I8 to EBCDIC (IBM-1047) */
0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
};
-EXTCONST unsigned char PL_e2utf[] = { /* EBCDIC (IBM-1047) to I8 */
+EXTCONST unsigned char PL_e2utf[] = { /* UTFEBCDIC (IBM-1047) to I8 */
0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
@@ -192,7 +192,7 @@ EXTCONST unsigned char PL_e2utf[] = { /* EBCDIC (IBM-1047) to I8 */
#endif /* 1047 */
#if '^' == 106 /* if defined(_OSD_POSIX) POSIX-BC */
-unsigned char PL_utf2e[] = { /* I8 to EBCDIC (POSIX-BC) */
+unsigned char PL_utf2e[] = { /* I8 to UTFEBCDIC (POSIX-BC) */
0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x15, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
@@ -211,7 +211,7 @@ unsigned char PL_utf2e[] = { /* I8 to EBCDIC (POSIX-BC) */
0xDC, 0xC0, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xDD, 0xFC, 0xE0, 0xFE
};
-unsigned char PL_e2utf[] = { /* EBCDIC (POSIX-BC) to I8 */
+unsigned char PL_e2utf[] = { /* UTFEBCDIC (POSIX-BC) to I8 */
0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
@@ -232,7 +232,7 @@ unsigned char PL_e2utf[] = { /* EBCDIC (POSIX-BC) to I8 */
#endif /* POSIX-BC */
#if '^' == 176 /* if defined(??) (OS/400?) 037 */
-unsigned char PL_utf2e[] = { /* I8 to EBCDIC (IBM-037) */
+unsigned char PL_utf2e[] = { /* I8 to UTFEBCDIC (IBM-037) */
0x00, 0x01, 0x02, 0x03, 0x37, 0x2D, 0x2E, 0x2F, 0x16, 0x05, 0x25, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x3C, 0x3D, 0x32, 0x26, 0x18, 0x19, 0x3F, 0x27, 0x1C, 0x1D, 0x1E, 0x1F,
0x40, 0x5A, 0x7F, 0x7B, 0x5B, 0x6C, 0x50, 0x7D, 0x4D, 0x5D, 0x5C, 0x4E, 0x6B, 0x60, 0x4B, 0x61,
@@ -251,7 +251,7 @@ unsigned char PL_utf2e[] = { /* I8 to EBCDIC (IBM-037) */
0xDC, 0xDD, 0xDE, 0xDF, 0xE1, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE
};
-unsigned char PL_e2utf[] = { /* EBCDIC (IBM-037) to I8 */
+unsigned char PL_e2utf[] = { /* UTFEBCDIC (IBM-037) to I8 */
0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
0x80, 0x81, 0x82, 0x83, 0x84, 0x0A, 0x17, 0x1B, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x05, 0x06, 0x07,
@@ -295,12 +295,6 @@ EXTCONST unsigned char PL_a2e[] = { /* ASCII (iso-8859-1) to EBCDIC (IBM-1047) *
0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
};
-#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0xDF
-#define LATIN_SMALL_LETTER_SHARP_S 0x59
-#define MICRO_SIGN 0xA0
-#define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE 0x0067
-#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE 0x0047
-
EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-1047) to ASCII (iso-8859-1) */
0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
@@ -377,12 +371,6 @@ EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (POSIX-BC) */
0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xC0, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
};
-#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0xDF
-#define LATIN_SMALL_LETTER_SHARP_S 0x59
-#define MICRO_SIGN 0xA0
-#define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE 0x0067
-#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE 0x0047
-
EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (POSIX-BC) to ASCII (ISO8859-1) */
0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x9D, 0x0A, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
@@ -459,13 +447,6 @@ EXTCONST unsigned char PL_a2e[] = { /* ASCII (ISO8859-1) to EBCDIC (IBM-037) */
0x8C, 0x49, 0xCD, 0xCE, 0xCB, 0xCF, 0xCC, 0xE1, 0x70, 0xDD, 0xDE, 0xDB, 0xDC, 0x8D, 0x8E, 0xDF
};
-
-#define LATIN_SMALL_LETTER_Y_WITH_DIAERESIS 0xDF
-#define LATIN_SMALL_LETTER_SHARP_S 0x59
-#define MICRO_SIGN 0xA0
-#define LATIN_CAPITAL_LETTER_A_WITH_RING_ABOVE 0x0067
-#define LATIN_SMALL_LETTER_A_WITH_RING_ABOVE 0x0047
-
EXTCONST unsigned char PL_e2a[] = { /* EBCDIC (IBM-037) to ASCII (ISO8859-1) */
0x00, 0x01, 0x02, 0x03, 0x9C, 0x09, 0x86, 0x7F, 0x97, 0x8D, 0x8E, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F,
0x10, 0x11, 0x12, 0x13, 0x9D, 0x85, 0x08, 0x87, 0x18, 0x19, 0x92, 0x8F, 0x1C, 0x1D, 0x1E, 0x1F,
@@ -522,6 +503,10 @@ EXTCONST unsigned char PL_fold[] = { /* fast EBCDIC case folding table, 'A' =>
};
#endif /* 037 */
+/* Since the EBCDIC code pages are isomorphic to Latin1, that table is merely a
+ * duplicate */
+EXTCONST unsigned char * PL_fold_latin1 = PL_fold;
+
#else
EXTCONST unsigned char PL_utf8skip[];
EXTCONST unsigned char PL_e2utf[];
@@ -529,12 +514,9 @@ EXTCONST unsigned char PL_utf2e[];
EXTCONST unsigned char PL_e2a[];
EXTCONST unsigned char PL_a2e[];
EXTCONST unsigned char PL_fold[];
+EXTCONST unsigned char * PL_fold_latin1;
#endif
-/* Since the EBCDIC code pages are isomorphic to Latin1, that table is merely a
- * duplicate */
-EXTCONST unsigned char * PL_fold_latin1 = PL_fold;
-
END_EXTERN_C
/* EBCDIC-happy ways of converting native code to UTF-8 */
@@ -560,8 +542,6 @@ END_EXTERN_C
Unicode Bit pattern 1st Byte 2nd Byte 3rd Byte 4th Byte 5th Byte 6th Byte 7th byte
U+0000..U+007F 000000000xxxxxxx 0xxxxxxx
U+0080..U+009F 00000000100xxxxx 100xxxxx
- U+00A0..U+00FF 00000000yyyxxxxx 11000yyy 101xxxxx
-
U+00A0..U+03FF 000000yyyyyxxxxx 110yyyyy 101xxxxx
U+0400..U+3FFF 00zzzzyyyyyxxxxx 1110zzzz 101yyyyy 101xxxxx
U+4000..U+3FFFF 0wwwzzzzzyyyyyxxxxx 11110www 101zzzzz 101yyyyy 101xxxxx
@@ -581,14 +561,17 @@ END_EXTERN_C
(uv) < 0x400000 ? 5 : \
(uv) < 0x4000000 ? 6 : 7 )
-
#define UNI_IS_INVARIANT(c) ((c) < 0xA0)
-/* UTF-EBCDIC semantic macros - transform back into I8 and then compare */
+
+/* UTF-EBCDIC semantic macros - transform back into I8 and then compare
+ * Comments as to the meaning of each are given at their corresponding utf8.h
+ * definitions */
#define UTF8_IS_START(c) (NATIVE_TO_UTF(c) >= 0xC5 && NATIVE_TO_UTF(c) != 0xE0)
#define UTF8_IS_CONTINUATION(c) ((NATIVE_TO_UTF(c) & 0xE0) == 0xA0)
#define UTF8_IS_CONTINUED(c) (NATIVE_TO_UTF(c) >= 0xA0)
#define UTF8_IS_DOWNGRADEABLE_START(c) (NATIVE_TO_UTF(c) >= 0xC5 && NATIVE_TO_UTF(c) <= 0xC7)
+#define UTF8_IS_ABOVE_LATIN1(c) (NATIVE_TO_I8(c) >= 0xC8)
#define UTF_START_MARK(len) (((len) > 7) ? 0xFF : ((U8)(0xFE << (7-(len)))))
#define UTF_START_MASK(len) (((len) >= 6) ? 0x01 : (0x1F >> ((len)-2)))
@@ -596,12 +579,25 @@ END_EXTERN_C
#define UTF_CONTINUATION_MASK ((U8)0x1f)
#define UTF_ACCUMULATION_SHIFT 5
+/* How wide can a single UTF-8 encoded character become in bytes. */
+/* NOTE: Strictly speaking Perl's UTF-8 should not be called UTF-8 since UTF-8
+ * is an encoding of Unicode, and Unicode's upper limit, 0x10FFFF, can be
+ * expressed with 5 bytes. However, Perl thinks of UTF-8 as a way to encode
+ * non-negative integers in a binary format, even those above Unicode */
+#define UTF8_MAXBYTES 7
+
+/* The maximum number of UTF-8 bytes a single Unicode character can
+ * uppercase/lowercase/fold into. Unicode guarantees that the maximum
+ * expansion is 3 characters. On EBCDIC platforms, the highest Unicode
+ * character occupies 5 bytes, therefore this number is 15 */
+#define UTF8_MAXBYTES_CASE 15
+
/*
* Local variables:
* c-indentation-style: bsd
* c-basic-offset: 4
- * indent-tabs-mode: t
+ * indent-tabs-mode: nil
* End:
*
- * ex: set ts=8 sts=4 sw=4 noet:
+ * ex: set ts=8 sts=4 sw=4 et:
*/